Don't Lose Entities from Retrieval to Generation: Dual Entity Recovery RAG for multi-hop QA

• URL: http://arxiv.org/abs/2609.06065v1
• Date: Sat, 05 Sep 2026 12:52:40 GMT
• Title: Don't Lose Entities from Retrieval to Generation: Dual Entity Recovery RAG for multi-hop QA
• Abstract summary: We show that both forms of decomposition share the same vulnerability, the loss of entity information, and that this loss breaks the pipeline at two separate points.<n>We propose Dual Entity Recovery RAG (DER-RAG), which keeps the grounding entity explicit from retrieval through to generation with two lightweight components.
• Score: 6.545870094085958
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented multi-hop question answering (QA) decomposes a query into sub-questions and decomposes the corpus into smaller retrieval units such as sentences. Both forms of decomposition improve the pipeline, but we show that both share the same vulnerability, the loss of entity information, and that this loss breaks the pipeline at two separate points. The first point is retrieval, where a sub-question loses the entity resolved at the previous hop, leaving the retriever with nothing to match against. The second point is harder to see, because retrieval still appears to succeed. Once a passage is split into sentences, an isolated sentence loses the context that grounds its pronouns, so even with the correct sentence in hand the LLM cannot tell which entity the sentence is about. We isolate this second point as a distinct failure mode that we call lost-in-generation, and a retrieval-controlled experiment shows that it degrades answers even when the gold evidence is fixed in the context. We then propose Dual Entity Recovery RAG (DER-RAG), which keeps the grounding entity explicit from retrieval through to generation with two lightweight components, a two-way query decomposition that carries the resolved entity across sub-questions and a subject entity prefix attached to each sentence at generation time. DER-RAG needs no graph construction, no corpus modification, and no fine-tuning, yet on three multi-hop QA benchmarks it matches or exceeds strong baselines, including graph-based methods that depend on costly offline structures.

Related papers

• Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering [48.94279718429342]
  We introduce Syfer, a framework for multilingual multi-hop question answering.<n>Syfer defers translation rather than applying it by default.<n> Experiments across multiple languages show that Syfer attains competitive accuracy.
  arXiv  Detail & Related papers  (2026-08-13T12:25:59Z)
• S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA [20.283357470094774]
  We propose S2G-RAG (Structured Sufficiency and Gap-judging RAG), an iterative framework with an explicit controller, S2G-Judge.<n>At each turn, S2G-Judge predicts whether the current evidence memory supports answering and, if not, outputs structured gap items that describe the missing information.<n>These gap items are then mapped into the next retrieval query, producing stable multi-turn retrieval trajectories.
  arXiv  Detail & Related papers  (2026-04-26T16:17:54Z)
• STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering [9.69666629029613]
  Multi-hop question answering (MHQA) enables accurate answers to complex queries by retrieving and reasoning over evidence dispersed across multiple documents.<n>Existing MHQA approaches mainly rely on iterative retrieval-augmented generation, which suffer from the following two major issues.<n>We propose STRIDE, a framework that separates strategic planning, dynamic control, and grounded execution.
  arXiv  Detail & Related papers  (2026-04-19T12:19:43Z)
• PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering [57.89576196160413]
  Large language models (LLMs) remain brittle on multi-hop question answering (MHQA)<n>We propose textbfPlanned Active Retrieval and Reasoning RAG (PAR$2$-RAG), a two-stage framework that separates emphcoverage from emphcommitment.
  arXiv  Detail & Related papers  (2026-03-30T23:52:54Z)
• MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries [2.756584457554517]
  Map-Disambiguate-Enrich-Reduce (MDER) generates context-derived triple descriptions and integrates them with entity-level summaries.<n>Decompose-Resolve (DR) decomposes user queries into resolvable triples and grounds them in the Knowledge Graph.<n>MDER and DR form an LLM-driven QA pipeline that is robust to sparse, incomplete, and complex relational data.
  arXiv  Detail & Related papers  (2026-03-11T18:38:44Z)
• CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering [15.281365738928415]
  Existing multi-hop RAG systems alternate between retrieval and reasoning at each step.<n>We propose CompactRAG, a framework that decouples offline corpus restructuring from online reasoning.<n>Experiments on HotpotQA, 2WikiMultiHopQA, and MuSiQue demonstrate that CompactRAG achieves competitive accuracy while substantially reducing token consumption.
  arXiv  Detail & Related papers  (2026-02-05T14:52:06Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• GRITHopper: Decomposition-Free Multi-Hop Dense Retrieval [52.47514434103737]
  We introduce GRITHopper-7B, a novel multi-hop dense retrieval model that achieves state-of-the-art performance.<n> GRITHopper combines generative and representational instruction tuning by integrating causal language modeling with dense retrieval training.<n>We find that incorporating additional context after the retrieval process, referred to as post-retrieval language modeling, enhances dense retrieval performance.
  arXiv  Detail & Related papers  (2025-03-10T16:42:48Z)
• Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering [25.544345244474073]
  ChainRAG is a progressive retrieval and rewriting method for multi-hop question answering.<n>It sequentially handles each sub-question by completing missing key entities and relevant sentences.<n>It consistently outperforms baselines in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2025-02-20T04:19:05Z)
• Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning [54.55643652781891]
  Open-Domain Conversational Question Answering (ODConvQA) aims at answering questions through a multi-turn conversation. We propose a method to directly predict answers with a phrase retrieval scheme for a sequence of words.
  arXiv  Detail & Related papers  (2023-06-07T09:46:38Z)
• Query Resolution for Conversational Search with Limited Supervision [63.131221660019776]
  We propose QuReTeC (Query Resolution by Term Classification), a neural query resolution model based on bidirectional transformers. We show that QuReTeC outperforms state-of-the-art models, and furthermore, that our distant supervision method can be used to substantially reduce the amount of human-curated data required to train QuReTeC.
  arXiv  Detail & Related papers  (2020-05-24T11:37:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.